Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gì
    -0.08
    işti
    -0.06
    Subject
    -0.06
    _AB
    -0.06
     amac
    -0.06
     eing
    -0.06
     MERCHANTABILITY
    -0.06
     pyt
    -0.06
    cısı
    -0.06
     king
    -0.06
    POSITIVE LOGITS
     Ville
    0.07
     Stevenson
    0.06
     REPLACE
    0.06
     vent
    0.06
     �
    0.06
    !==
    0.06
     partition
    0.06
    имо
    0.06
     매매
    0.06
     Snapchat
    0.06
    Act Density 0.013%

    No Known Activations